Introductory Remarks

Abstract

The notion ‘cognitive vision system (CogVS)’ stimulates a wide spectrum of associations. In many cases, the attribute ‘cognitive’ is related to advanced abilities of living creatures, in particular of primates. In this context, a close association between the terms ‘cognitive’ and ‘vision’ appears natural, because it is well known that vision constitutes the primate sensory channel with the largest spatiotemporal bandwidth.

Since the middle of the last century, technical means were gradually developed to record and process digitized image sequences. These technical advances created a seemingly unresistable challenge to devise algorithmic approaches which explain, simulate, or even surpass vision capabilities of living creatures. In this context, ‘vision’ is understood to refer to a set of information processing steps which transform the light intensity distribution impinging onto the transducer surface eventually into some kind of re-action, be it an observable movement, some acoustical communication, or a change of internal representations for the union of the depicted scene and the ‘vision system’ itself. The common understanding of ‘vision’ as a kind of information processing induces the use of the word ‘system’ in this context for whatever performs these processing steps – be it a living creature, a familiar digital computer, or any other alternative to realize a computational device.